Media Analytics

Read our publications from our Media Analytics team who are overcoming fundamental challenges in computer vision and are addressing critical needs in mobility, security, safety and socially relevant AI. Our team solves fundamental challenges in computer vision, with a focus on understanding and interaction in 3D scenes, representation learning in visual and multimodal data, learning across domains and tasks, as well as responsible AI. Our technological breakthroughs contribute to socially-relevant solutions that address key enterprise needs in mobility, safety and smart spaces.

Posts

Video Person Re-Identification using Learned Clip Similarity Aggregation

We address the challenging task of video-based person re-identification. Recent works have shown that splitting the video sequences into clips and then aggregating clip-based similarity is appropriate for the task. We show that using a learned clip similarity aggregation function allows filtering out hard clip pairs, e.g. where the person is not clearly visible, is in a challenging pose, or where the poses in the two clips are too different to be informative. This allows the method to focus on clip-pairs which are more informative for the task. We also introduce the use of 3D CNNs for video-based re-identification and show their effectiveness by performing equivalent to previous works, which use optical flow in addition to RGB, while using RGB inputs only. We give quantitative results on three challenging public benchmarks and show better or competitive performance. We also validate our method qualitatively.

Adversarial Learning of Privacy-Preserving and Task-Oriented Representations

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model inversion attack, whose goal is to reconstruct the input data from the latent representation of deep networks. Our work aims at learning a privacy-preserving and task-oriented representation to defend against such model inversion attacks. Specifically, we propose an adversarial reconstruction learning framework that prevents the latent representations decoded into original input data. By simulating the expected behavior of adversary, our framework is realized by minimizing the negative pixel reconstruction loss or the negative feature reconstruction (i.e., perceptual distance) loss. We validate the proposed method on face attribute prediction, showing that our method allows protecting visual privacy with a small decrease in utility performance. In addition, we show the utility-privacy trade-off with different choices of hyperparameter for negative perceptual distance loss at training, allowing service providers to determine the right level of privacy-protection with a certain utility performance. Moreover, we provide an extensive study with different selections of features, tasks, and the data to further analyze their influence on privacy protection.

Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM

Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of such techniques to modern Simultaneous Localization And Mapping (SLAM) systems, especially in driving scenarios. In this paper, we revisit the geometric approach to this problem, and provide a theoretical proof that explicitly shows the ambiguity between radial distortion and scene depth when two-view geometry is used to self-calibrate the radial distortion. In view of such geometric degeneracy, we propose a learning approach that trains a convolutional neural network (CNN) on a large amount of synthetic data. We demonstrate the utility of our proposed method by applying it as a checkerboard-free calibration tool for SLAM, achieving comparable or superior performance to previous learning and hand-crafted method

Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles

We address the problem of 3D object detection from 2D monocular images in autonomous driving scenarios. We propose to lift the 2D images to 3D representations using learned neural networks and leverage existing networks working directly on 3D data to perform 3D object detection and localization. We show that, with carefully designed training mechanism and automatically selected minimally noisy data, such a method is not only feasible, but gives higher results than many methods working on actual 3D inputs acquired from physical sensors. On the challenging KITTI benchmark, we show that our 2D to 3D lifted method outperforms many recent competitive 3D networks while significantly outperforming previous state-of-the-art for 3D detection from monocular images. We also show that a late fusion of the output of the network trained on generated 3D images, with that trained on real 3D images, improves performance. We find the results very interesting and argue that such a method could serve as a highly reliable backup in case of malfunction of expensive 3D sensors, if not potentially making them redundant, at least in the case of low human injury risk autonomous navigation scenarios like warehouse automation.

Domain Adaptation for Structured Output via Discriminative Patch Representations

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not generalize well to other domains without annotations for model finetuning. To avoid the labor-intensive process of annotation, we develop a domain adaptation method to adapt the source data to the unlabeled target domain. We propose to learn discriminative feature representations of patches in the source domain by discovering multiple modes of patch-wise output distribution through the construction of a clustered space. With such representations as guidance, we use an adversarial learning scheme to push the feature representations of target patches in the clustered space closer to the distributions of source patches. In addition, we show that our framework is complementary to existing domain adaptation techniques and achieves consistent improvements on semantic segmentation. Extensive ablations and results are demonstrated on numerous benchmark datasets with various settings, such as synthetic-to-real and cross-city scenarios.

GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition

Traditional intrinsic image decomposition focuses on decomposing images into reflectance and shading, leaving surfaces normals and lighting entangled in shading. In this work, we propose a Global-Local Spherical Harmonics (GLoSH) lighting model to improve the lighting component, and jointly predict reflectance and surface normals. The global SH models the holistic lighting while local SH account for the spatial variation of lighting. Also, a novel non-negative lighting constraint is proposed to encourage the estimated SH to be physically meaningful. To seamlessly reflect the GLoSH model, we design a coarse-to-fine network structure. The coarse network predicts global SH, reflectance and normals, and the fine network predicts their local residuals. Lacking labels for reflectance and lighting, we apply synthetic data for model pre-training and fine-tune the model with real data in a self-supervised way. Compared to the state-of-the-art methods only targeting normals or reflectance and shading, our method recovers all components and achieves consistently better results on three real datasets, IIW, SAW and NYUv2.

Deep Supervision with Intermediate Concepts (IEEE)

Read Deep Supervision with Intermediate Concepts (IEEE). Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human and machine vision suggest that there are often intermediate representations that are intrinsic to an inference task, and which provide essential structure to improve generalization. In this work, we explore an approach for injecting prior domain structure into neural network training by supervising hidden layers of a CNN with intermediate concepts that normally are not observed in practice. We formulate a probabilistic framework which formalizes these notions and predicts improved generalization via this deep supervision method. One advantage of this approach is that we are able to train only from synthetic CAD renderings of cluttered scenes, where concept values can be extracted, but apply the results to real images. Our implementation achieves the state-of-the-art performance of 2D/3D keypoint localization and image classification on real image benchmarks including KITTI, PASCALVOC, PASCAL3D+, IKEA, and CIFAR100. We provide additional evidence that our approach outperforms alternative forms of supervision, such as multi-task networks.

Pose-variant 3D Facial Attribute Generation

We address the challenging problem of generating facial attributes using a single image in an unconstrained pose. In contrast to prior works that largely consider generation on 2D near-frontal images, we propose a GAN-based framework to generate attributes directly on a dense 3D representation given by UV texture and position maps, resulting in photorealistic, geometrically-consistent and identity-preserving outputs. Starting from a self-occluded UV texture map obtained by applying an off-the-shelf 3D reconstruction method, we propose two novel components. First, a texture completion generative adversarial network (TC-GAN) completes the partial UV texture map. Second, a 3D attribute generation GAN (3DA-GAN) synthesizes the target attribute while obtaining an appearance consistent with 3D face geometry and preserving identity. Extensive experiments on CelebA, LFW and IJB-A show that our method achieves consistently better attribute generation accuracy than prior methods, a higher degree of qualitative photorealism and preserves face identity information.

A Dataset for High-Level 3D Scene Understanding of Complex Road Scenes in the Top-View

We introduce a novel dataset for high-level 3D scene understanding of complex road scenes. Our annotations extend the existing datasets KITTI [5] and nuScenes [1] with semantically and geometrically meaningful attributes like the number of lanes or the existence of, and distance to, intersections, sidewalks and crosswalks. Our attributes are rich enough to build a meaningful representation of the scene in the top-view and provide a tangible interface to the real world for several practical applications.

A Parametric Top-View Representation of Complex Road Scenes

In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model of road layouts in a top-view representation, which is not only intuitive for human visualization but also provides an interpretable interface for higher-level decision making. Moreover, the design of our top-view scene model allows for efficient sampling and thus generation of large-scale simulated data, which we leverage to train a deep neural network to infer our scene model’s parameters. Specifically, our proposed training procedure uses supervised domain-adaptation techniques to incorporate both simulated as well as manually annotated data. Finally, we design a Conditional Random Field (CRF) that enforces coherent predictions for a single frame and encourages temporal smoothness among video frames. Experiments on two public data sets show that: (1) Our parametric top-view model is representative enough to describe complex road scenes; (2) The proposed method outperforms baselines trained on manually-annotated or simulated data only, thus getting the best of both; (3) Our CRF is able to generate temporally smoothed while semantically meaningful results.